Merge branch 'master' into collect-tests

Author: ahsan-z-khan

CHANGELOG.md

@@ -1,5 +1,22 @@
 # Changelog
 
+## v2.24.0 (2021-01-22)
+
+### Features
+
+ * add support for Std:Join for pipelines
+ * Map image name to image uri
+ * friendly names for short URIs
+
+### Bug Fixes and Other Changes
+
+ * increase allowed time for search to get updated
+ * refactor distribution config construction
+
+### Documentation Changes
+
+ * Add SMP 1.2.0 API docs
+
 ## v2.23.6 (2021-01-20)
 
 ### Bug Fixes and Other Changes

VERSION

@@ -1 +1 @@
-2.23.7.dev0
+2.24.1.dev0

doc/api/training/smp_versions/v1.2.0/smd_model_parallel_pytorch.rst

@@ -140,16 +140,16 @@ This API document assumes you use the following import statements in your traini
       computation. \ ``bucket_cap_mb``\ controls the bucket size in MegaBytes
       (MB).
 
-    - ``trace_memory_usage`` (default: False): When set to True, the library attempts
+   -  ``trace_memory_usage`` (default: False): When set to True, the library attempts
       to measure memory usage per module during tracing. If this is disabled,
       memory usage will be estimated through the sizes of tensors returned from
       the module.
 
-    - ``broadcast_buffers`` (default: True): Flag to be used with ``ddp=True``.
+   -  ``broadcast_buffers`` (default: True): Flag to be used with ``ddp=True``.
       This parameter is forwarded to the underlying ``DistributedDataParallel`` wrapper.
       Please see: `broadcast_buffer <https://pytorch.org/docs/stable/generated/torch.nn.parallel.DistributedDataParallel.html#torch.nn.parallel.DistributedDataParallel>`__.
 
-    - ``gradient_as_bucket_view (PyTorch 1.7 only)`` (default: False): To be
+   -  ``gradient_as_bucket_view (PyTorch 1.7 only)`` (default: False): To be
       used with ``ddp=True``. This parameter is forwarded to the underlying
       ``DistributedDataParallel`` wrapper. Please see `gradient_as_bucket_view <https://pytorch.org/docs/stable/generated/torch.nn.parallel.DistributedDataParallel.html#torch.nn.parallel.DistributedDataParallel>`__.
 

src/sagemaker/estimator.py

@@ -49,6 +49,7 @@
     UploadedCode,
     validate_source_dir,
     _region_supports_debugger,
+    _region_supports_profiler,
     get_mp_parameters,
 )
 from sagemaker.inputs import TrainingInput
@@ -494,7 +495,7 @@ def _prepare_profiler_for_training(self):
         """Set necessary values and do basic validations in profiler config and profiler rules.
 
         When user explicitly set rules to an empty list, default profiler rule won't be enabled.
-        Default profiler rule will be enabled when either:
+        Default profiler rule will be enabled in supported regions when either:
         1. user doesn't specify any rules, i.e., rules=None; or
         2. user only specify debugger rules, i.e., rules=[Rule.sagemaker(...)]
         """
@@ -503,7 +504,7 @@ def _prepare_profiler_for_training(self):
                 raise RuntimeError("profiler_config cannot be set when disable_profiler is True.")
             if self.profiler_rules:
                 raise RuntimeError("ProfilerRule cannot be set when disable_profiler is True.")
-        elif _region_supports_debugger(self.sagemaker_session.boto_region_name):
+        elif _region_supports_profiler(self.sagemaker_session.boto_region_name):
             if self.profiler_config is None:
                 self.profiler_config = ProfilerConfig(s3_output_path=self.output_path)
             if self.rules is None or (self.rules and not self.profiler_rules):

src/sagemaker/fw_utils.py

@@ -49,6 +49,8 @@
 )
 
 DEBUGGER_UNSUPPORTED_REGIONS = ("us-iso-east-1",)
+PROFILER_UNSUPPORTED_REGIONS = ("us-iso-east-1", "cn-north-1", "cn-northwest-1")
+
 SINGLE_GPU_INSTANCE_TYPES = ("ml.p2.xlarge", "ml.p3.2xlarge")
 SM_DATAPARALLEL_SUPPORTED_INSTANCE_TYPES = (
     "ml.p3.16xlarge",
@@ -550,6 +552,19 @@ def _region_supports_debugger(region_name):
     return region_name.lower() not in DEBUGGER_UNSUPPORTED_REGIONS
 
 
+def _region_supports_profiler(region_name):
+    """Returns bool indicating whether region supports Amazon SageMaker Debugger profiling feature.
+
+    Args:
+        region_name (str): Name of the region to check against.
+
+    Returns:
+        bool: Whether or not the region supports Amazon SageMaker Debugger profiling feature.
+
+    """
+    return region_name.lower() not in PROFILER_UNSUPPORTED_REGIONS
+
+
 def validate_version_or_image_args(framework_version, py_version, image_uri):
     """Checks if version or image arguments are specified.
 

tests/integ/test_experiments_analytics.py

@@ -38,6 +38,17 @@ def experiment(sagemaker_session):
 
         time.sleep(15)  # wait for search to get updated
 
+        # allow search time thrice
+        for _ in range(3):
+            analytics = ExperimentAnalytics(
+                experiment_name=experiment_name, sagemaker_session=sagemaker_session
+            )
+
+            if len(analytics.dataframe().columns) > 0:
+                break
+
+            time.sleep(15)
+
         yield experiment_name
     finally:
         _delete_resources(sm, experiment_name, trials)
@@ -79,6 +90,17 @@ def experiment_with_artifacts(sagemaker_session):
 
         time.sleep(15)  # wait for search to get updated
 
+        # allow search time thrice
+        for _ in range(3):
+            analytics = ExperimentAnalytics(
+                experiment_name=experiment_name, sagemaker_session=sagemaker_session
+            )
+
+            if len(analytics.dataframe().columns) > 0:
+                break
+
+            time.sleep(15)
+
         yield experiment_name
     finally:
         _delete_resources(sm, experiment_name, trials)

tests/unit/test_estimator.py

@@ -35,6 +35,7 @@
     Rule,
 )
 from sagemaker.estimator import Estimator, EstimatorBase, Framework, _TrainingJob
+from sagemaker.fw_utils import PROFILER_UNSUPPORTED_REGIONS
 from sagemaker.inputs import ShuffleConfig
 from sagemaker.model import FrameworkModel
 from sagemaker.predictor import Predictor
@@ -632,6 +633,32 @@ def test_framework_with_profiler_config_without_s3_output_path(time, sagemaker_s
     ]
 
 
+@pytest.mark.parametrize("region", PROFILER_UNSUPPORTED_REGIONS)
+def test_framework_with_no_default_profiler_in_unsupported_region(region):
+    boto_mock = Mock(name="boto_session", region_name=region)
+    sms = MagicMock(
+        name="sagemaker_session",
+        boto_session=boto_mock,
+        boto_region_name=region,
+        config=None,
+        local_mode=False,
+        s3_client=None,
+        s3_resource=None,
+    )
+    f = DummyFramework(
+        entry_point=SCRIPT_PATH,
+        role=ROLE,
+        sagemaker_session=sms,
+        instance_count=INSTANCE_COUNT,
+        instance_type=INSTANCE_TYPE,
+    )
+    f.fit("s3://mydata")
+    sms.train.assert_called_once()
+    _, args = sms.train.call_args
+    assert args.get("profiler_config") is None
+    assert args.get("profiler_rule_configs") is None
+
+
 def test_framework_with_profiler_config_and_profiler_disabled(sagemaker_session):
     with pytest.raises(RuntimeError) as error:
         f = DummyFramework(